© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 10702
    Prev
    Next
    INDEX
    Explanations

    html element id

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ोर
    0.44
    <0x9B>
    0.41
    บริ
    0.36
    یں
    0.35
    <0xA2>
    0.34
    <0xB6>
    0.34
    водить
    0.34
     BRCA
    0.33
    <0xAC>
    0.33
     वा
    0.33
    POSITIVE LOGITS
    my
    0.53
    carouselExample
    0.48
    navbarSupported
    0.47
    example
    0.44
    myForm
    0.42
     my
    0.42
    sendMessage
    0.42
     例如
    0.40
     josé
    0.40
     ejemplo
    0.39
    Activations Density 0.006%

    No Known Activations